{"title":"用联合释义学习推进Seq2seq","authors":"So Yeon Min, Preethi Raghavan, Peter Szolovits","doi":"10.18653/v1/2020.clinicalnlp-1.30","DOIUrl":null,"url":null,"abstract":"We address the problem of model generalization for sequence to sequence (seq2seq) architectures. We propose going beyond data augmentation via paraphrase-optimized multi-task learning and observe that it is useful in correctly handling unseen sentential paraphrases as inputs. Our models greatly outperform SOTA seq2seq models for semantic parsing on diverse domains (Overnight - up to 3.2% and emrQA - 7%) and Nematus, the winning solution for WMT 2017, for Czech to English translation (CzENG 1.6 - 1.5 BLEU).","PeriodicalId":216954,"journal":{"name":"Clinical Natural Language Processing Workshop","volume":"40 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Advancing Seq2seq with Joint Paraphrase Learning\",\"authors\":\"So Yeon Min, Preethi Raghavan, Peter Szolovits\",\"doi\":\"10.18653/v1/2020.clinicalnlp-1.30\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We address the problem of model generalization for sequence to sequence (seq2seq) architectures. We propose going beyond data augmentation via paraphrase-optimized multi-task learning and observe that it is useful in correctly handling unseen sentential paraphrases as inputs. Our models greatly outperform SOTA seq2seq models for semantic parsing on diverse domains (Overnight - up to 3.2% and emrQA - 7%) and Nematus, the winning solution for WMT 2017, for Czech to English translation (CzENG 1.6 - 1.5 BLEU).\",\"PeriodicalId\":216954,\"journal\":{\"name\":\"Clinical Natural Language Processing Workshop\",\"volume\":\"40 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Clinical Natural Language Processing Workshop\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/2020.clinicalnlp-1.30\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Natural Language Processing Workshop","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/2020.clinicalnlp-1.30","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
We address the problem of model generalization for sequence to sequence (seq2seq) architectures. We propose going beyond data augmentation via paraphrase-optimized multi-task learning and observe that it is useful in correctly handling unseen sentential paraphrases as inputs. Our models greatly outperform SOTA seq2seq models for semantic parsing on diverse domains (Overnight - up to 3.2% and emrQA - 7%) and Nematus, the winning solution for WMT 2017, for Czech to English translation (CzENG 1.6 - 1.5 BLEU).
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
